Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    values and brain regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ate
    0.55
    ↵
    0.52
    Modal
    0.51
    mills
    0.50
    ot
    0.49
    ham
    0.48
    namen
    0.47
    binary
    0.46
    chefs
    0.46
    mau
    0.46
    POSITIVE LOGITS
     ottenere
    0.55
    แ
    0.52
     coisa
    0.50
     defaul
    0.48
    จ
    0.48
     implement
    0.47
    অ
    0.47
     jit
    0.47
     enero
    0.46
     TLS
    0.46
    Act Density 0.001%

    No Known Activations